Text Generation
Transformers
GGUF
English
llama
llama3
dementia
healthcare
medical
caregiving
alzheimers
memory-care
assistant
fine-tuned
specialized
conversational
4-bit precision
gptq
Instructions to use splendidcomputer/new-dim with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use splendidcomputer/new-dim with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="splendidcomputer/new-dim") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("splendidcomputer/new-dim") model = AutoModelForMultimodalLM.from_pretrained("splendidcomputer/new-dim") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - llama-cpp-python
How to use splendidcomputer/new-dim with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="splendidcomputer/new-dim", filename="model.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use splendidcomputer/new-dim with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf splendidcomputer/new-dim # Run inference directly in the terminal: llama-cli -hf splendidcomputer/new-dim
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf splendidcomputer/new-dim # Run inference directly in the terminal: llama-cli -hf splendidcomputer/new-dim
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf splendidcomputer/new-dim # Run inference directly in the terminal: ./llama-cli -hf splendidcomputer/new-dim
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf splendidcomputer/new-dim # Run inference directly in the terminal: ./build/bin/llama-cli -hf splendidcomputer/new-dim
Use Docker
docker model run hf.co/splendidcomputer/new-dim
- LM Studio
- Jan
- vLLM
How to use splendidcomputer/new-dim with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "splendidcomputer/new-dim" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "splendidcomputer/new-dim", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/splendidcomputer/new-dim
- SGLang
How to use splendidcomputer/new-dim with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "splendidcomputer/new-dim" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "splendidcomputer/new-dim", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "splendidcomputer/new-dim" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "splendidcomputer/new-dim", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use splendidcomputer/new-dim with Ollama:
ollama run hf.co/splendidcomputer/new-dim
- Unsloth Studio
How to use splendidcomputer/new-dim with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for splendidcomputer/new-dim to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for splendidcomputer/new-dim to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for splendidcomputer/new-dim to start chatting
- Atomic Chat new
- Docker Model Runner
How to use splendidcomputer/new-dim with Docker Model Runner:
docker model run hf.co/splendidcomputer/new-dim
- Lemonade
How to use splendidcomputer/new-dim with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull splendidcomputer/new-dim
Run and chat with the model
lemonade run user.new-dim-{{QUANT_TAG}}List all available models
lemonade list
| # Script to prepare Ollama model for Hugging Face upload | |
| # This script helps export the Ollama model and prepare it for Hugging Face | |
| set -e | |
| MODEL_NAME="llama3-dementia-care:latest" | |
| EXPORT_DIR="./model_export" | |
| CURRENT_DIR=$(pwd) | |
| echo "π Preparing Llama 3 Dementia Care model for Hugging Face upload..." | |
| echo "==================================================" | |
| # Check if Ollama is installed | |
| if ! command -v ollama &> /dev/null; then | |
| echo "β Error: Ollama is not installed or not in PATH" | |
| echo "Please install Ollama first: https://ollama.com" | |
| exit 1 | |
| fi | |
| # Check if the model exists | |
| if ! ollama list | grep -q "$MODEL_NAME"; then | |
| echo "β Error: Model $MODEL_NAME not found" | |
| echo "Available models:" | |
| ollama list | |
| exit 1 | |
| fi | |
| echo "β Found model: $MODEL_NAME" | |
| # Create export directory | |
| mkdir -p "$EXPORT_DIR" | |
| cd "$EXPORT_DIR" | |
| echo "π Created export directory: $EXPORT_DIR" | |
| # Export model information | |
| echo "π Exporting model information..." | |
| ollama show "$MODEL_NAME" > model_details.txt | |
| ollama show "$MODEL_NAME" --modelfile > exported_modelfile.txt | |
| echo "π Model details saved to:" | |
| echo " - model_details.txt" | |
| echo " - exported_modelfile.txt" | |
| # Create a README for the export | |
| cat > export_README.md << 'EOF' | |
| # Exported Ollama Model Files | |
| This directory contains the exported files from your Ollama model that need to be converted for Hugging Face. | |
| ## Files: | |
| - `model_details.txt` - Detailed model information from Ollama | |
| - `exported_modelfile.txt` - The Modelfile configuration | |
| - `export_README.md` - This file | |
| ## Next Steps: | |
| ### Option 1: Manual Conversion | |
| 1. You'll need to manually extract the model weights from Ollama's blob storage | |
| 2. Convert them to PyTorch/Safetensors format | |
| 3. Create proper tokenizer files | |
| ### Option 2: Use Conversion Tools | |
| 1. Install ollama-python: `pip install ollama` | |
| 2. Use conversion scripts like: | |
| - https://github.com/ollama/ollama/blob/main/docs/modelfile.md | |
| - Community conversion tools | |
| ### Option 3: Re-train/Fine-tune | |
| 1. Start with the base Llama 3 8B model from Hugging Face | |
| 2. Fine-tune it with your dementia care dataset | |
| 3. Upload the fine-tuned model | |
| ## Important Notes: | |
| - Ollama stores models in a specific format that may require conversion | |
| - The model weights are typically in `/Users/[username]/.ollama/models/blobs/` | |
| - You may need to use specialized tools to extract and convert the weights | |
| For more information, visit: https://ollama.com/blog/modelfile | |
| EOF | |
| echo "π Created export_README.md with next steps" | |
| # Try to locate the actual model blob | |
| echo "π Locating model blob files..." | |
| OLLAMA_MODELS_DIR="$HOME/.ollama/models" | |
| if [ -d "$OLLAMA_MODELS_DIR" ]; then | |
| echo "π Ollama models directory: $OLLAMA_MODELS_DIR" | |
| # Extract the blob SHA from the Modelfile | |
| BLOB_SHA=$(grep "^FROM" exported_modelfile.txt | grep "sha256" | awk -F'sha256-' '{print $2}') | |
| if [ -n "$BLOB_SHA" ]; then | |
| echo "π Model blob SHA: $BLOB_SHA" | |
| BLOB_PATH="$OLLAMA_MODELS_DIR/blobs/sha256-$BLOB_SHA" | |
| if [ -f "$BLOB_PATH" ]; then | |
| echo "β Found model blob: $BLOB_PATH" | |
| echo "π Blob size: $(ls -lh "$BLOB_PATH" | awk '{print $5}')" | |
| # Copy blob info to export | |
| echo "Model Blob Information:" > blob_info.txt | |
| echo "SHA256: $BLOB_SHA" >> blob_info.txt | |
| echo "Path: $BLOB_PATH" >> blob_info.txt | |
| echo "Size: $(ls -lh "$BLOB_PATH" | awk '{print $5}')" >> blob_info.txt | |
| echo "Modified: $(ls -l "$BLOB_PATH" | awk '{print $6, $7, $8}')" >> blob_info.txt | |
| else | |
| echo "β Model blob not found at expected location" | |
| fi | |
| else | |
| echo "β Could not extract blob SHA from Modelfile" | |
| fi | |
| else | |
| echo "β Ollama models directory not found" | |
| fi | |
| cd "$CURRENT_DIR" | |
| echo "" | |
| echo "π Export preparation complete!" | |
| echo "==================================================" | |
| echo "π Files exported to: $EXPORT_DIR" | |
| echo "" | |
| echo "β οΈ IMPORTANT: Converting Ollama models to Hugging Face format requires additional steps:" | |
| echo "" | |
| echo "π Conversion Options:" | |
| echo "1. Use ollama-python and conversion tools" | |
| echo "2. Extract and convert model weights manually" | |
| echo "3. Re-train using the base Llama 3 model on Hugging Face" | |
| echo "" | |
| echo "π Resources:" | |
| echo "- Ollama documentation: https://ollama.com/blog/modelfile" | |
| echo "- Hugging Face model upload: https://huggingface.co/docs/transformers/model_sharing" | |
| echo "" | |
| echo "β Your repository structure is ready for Hugging Face!" | |
| echo "π Repository files created:" | |
| ls -la "$CURRENT_DIR" | grep -E '\.(md|json|txt|py)$|Modelfile|NOTICE' | |
| echo "" | |
| echo "π Next: Upload your repository to Hugging Face and add the converted model weights." | |